SteinerSQL: Graph-Guided Mathematical Reasoning for Text-to-SQL Generation

• URL: http://arxiv.org/abs/2509.19623v1
• Date: Tue, 23 Sep 2025 22:30:52 GMT
• Title: SteinerSQL: Graph-Guided Mathematical Reasoning for Text-to-SQL Generation
• Authors: Xutao Mao, Tao Liu, Hongying Zan,
• Abstract summary: Existing methods often tackle these challenges in isolation, creating a fractured reasoning process.<n>We introduce Steiner, a framework that unifies these dual challenges into a single, graph-centric optimization problem.<n>Steiner operates in three stages: mathematical decomposition to identify required tables (terminals), optimal reasoning construction via a Steiner tree problem, and multi-level validation to ensure correctness.
• Score: 4.487121236852947
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Language Models (LLMs) struggle with complex Text-to-SQL queries that demand both sophisticated mathematical reasoning and intricate schema navigation. Existing methods often tackle these challenges in isolation, creating a fractured reasoning process that compromises logical and structural correctness. To resolve this, we introduce SteinerSQL, a framework that unifies these dual challenges into a single, graph-centric optimization problem. SteinerSQL operates in three stages: mathematical decomposition to identify required tables (terminals), optimal reasoning scaffold construction via a Steiner tree problem, and multi-level validation to ensure correctness. On the challenging LogicCat and Spider2.0-Lite benchmarks, SteinerSQL establishes a new state-of-the-art with 36.10% and 40.04% execution accuracy, respectively, using Gemini-2.5-Pro. Beyond accuracy, SteinerSQL presents a new, unified paradigm for Text-to-SQL, paving the way for more robust and principled solutions to complex reasoning tasks.

Related papers

• Monte Carlo Tree Search with Reasoning Path Refinement for Small Language Models in Conversational Text-to-NoSQL [20.156191782890797]
  We introduce the Conversational Text-to-No task, which generates queries given a natural language question, a database, and a dialogue history.<n>We propose Stage-MCTS, a framework that endows small language models with query-specific reasoning capabilities.<n>Our approach outperforms state-of-the-art large reasoning models, improving execution value match accuracy by up to 7.93%.
  arXiv  Detail & Related papers  (2026-02-13T03:35:38Z)
• Text-to-SQL as Dual-State Reasoning: Integrating Adaptive Context and Progressive Generation [54.53145282349042]
  We introduce DSR-sourced, a textbfDual-textbfS textbfReasoning framework that models Text-to-context as an interaction between an adaptive context state and a progressive generation state.<n>Without any post-training or in-context examples, DSR-sourced achieves competitive performance, reaching 35.28% execution accuracy on Spider 2.0-Snow and 68.32% on BIRD development set.
  arXiv  Detail & Related papers  (2025-11-26T13:52:50Z)
• CogniSQL-R1-Zero: Lightweight Reinforced Reasoning for Efficient SQL Generation [1.169202600932732]
  We introduce Cogni-R1-Zero, a reinforcement learning (RL) framework and model.<n>We use a lightweight reward signal based on execution correctness and format-tag compliance.<n>Our method achieves state-of-the-art execution accuracy on Text2 benchmark.<n>To support further research in efficient and interpretable Text-to-code modeling, we release two curated datasets.
  arXiv  Detail & Related papers  (2025-07-08T14:17:07Z)
• LogicCat: A Chain-of-Thought Text-to-SQL Benchmark for Complex Reasoning [12.249447967086828]
  LogicCat is the first Text-to-sense benchmark dataset specifically designed for complex reasoning and chain-of-thought parsing.<n>We show that LogicCat substantially increases the task difficulty for current state-of-the-art models to 33.20% execution accuracy.
  arXiv  Detail & Related papers  (2025-05-24T15:23:43Z)
• UNJOIN: Enhancing Multi-Table Text-to-SQL Generation via Schema Simplification [50.59009084277447]
  We introduce UNJOIN, a framework that decouples the retrieval of schema elements from logic generation.<n>In the first stage, we merge the column names of all tables in the database into a single-table representation by prefixing each column with its table name.<n>In the second stage, the query is generated on this simplified schema and mapped back to the original schema by reconstructing JOINs, UNIONs, and relational logic.
  arXiv  Detail & Related papers  (2025-05-23T17:28:43Z)
• PTD-SQL: Partitioning and Targeted Drilling with LLMs in Text-to-SQL [54.304872649870575]
  Large Language Models (LLMs) have emerged as powerful tools for Text-to-sense tasks. In this study, we propose that employing query group partitioning allows LLMs to focus on learning the thought processes specific to a single problem type.
  arXiv  Detail & Related papers  (2024-09-21T09:33:14Z)
• SelECT-SQL: Self-correcting ensemble Chain-of-Thought for Text-to-SQL [3.422309388045878]
  We introduce SelECT-, a novel in-context learning solution that uses an algorithmic combination of chain-of-thought, self-correction, and ensemble methods. Specifically, when configured using GPT as the base LLM, SelECT-Turbo achieves 84.2% execution accuracy on the Spider leaderboard's development set.
  arXiv  Detail & Related papers  (2024-09-16T05:40:18Z)
• SQL-PaLM: Improved Large Language Model Adaptation for Text-to-SQL (extended) [53.95151604061761]
  This paper introduces the framework for enhancing Text-to- filtering using large language models (LLMs) With few-shot prompting, we explore the effectiveness of consistency decoding with execution-based error analyses. With instruction fine-tuning, we delve deep in understanding the critical paradigms that influence the performance of tuned LLMs.
  arXiv  Detail & Related papers  (2023-05-26T21:39:05Z)
• UNITE: A Unified Benchmark for Text-to-SQL Evaluation [72.72040379293718]
  We introduce a UNIfied benchmark for Text-to-domain systems. It is composed of publicly available text-to-domain datasets and 29K databases. Compared to the widely used Spider benchmark, we introduce a threefold increase in SQL patterns.
  arXiv  Detail & Related papers  (2023-05-25T17:19:52Z)
• Conversational Text-to-SQL: An Odyssey into State-of-the-Art and Challenges Ahead [6.966624873109535]
  State-of-the-art (SOTA) systems use large, pre-trained and finetuned language models, such as the T5-family. With multi-tasking (MT) over coherent tasks with discrete prompts during training, we improve over specialized text-to-three models. We conduct studies to tease apart errors attributable to domain and compositional generalization.
  arXiv  Detail & Related papers  (2023-02-21T23:15:33Z)
• S$^2$SQL: Injecting Syntax to Question-Schema Interaction Graph Encoder for Text-to-SQL Parsers [66.78665327694625]
  We propose S$2$, injecting Syntax to question- encoder graph for Text-to- relational parsing. We also employ the decoupling constraint to induce diverse edge embedding, which further improves the network's performance. Experiments on the Spider and robustness setting Spider-Syn demonstrate that the proposed approach outperforms all existing methods when pre-training models are used.
  arXiv  Detail & Related papers  (2022-03-14T09:49:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.